Improved deep learning techniques for recognition and labeling
Representing images in robust, discriminative and informative features is deemed to be crucial for good recognition performance on many fundamental computer vision problems such as semantic attribute prediction and semantic image segmentation. Researchers tend to rely on hand-crafted features like S...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/72748 |